© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14810
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person (likely a character or figure) named "Manziel" in a story

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    67
    +0.15
    0.6%
    1516
    +0.15
    0.6%
    1256
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1516
    +0.15
    0.05
    67
    +0.15
    0.04
    1950
    +0.13
    0.04
    Negative Logits
    celona
    -0.58
    harmed
    -0.54
    <bos>
    -0.50
    solicited
    -0.49
     село
    -0.48
     resolve
    -0.48
    Atsauces
    -0.47
    HostException
    -0.45
    INVISIBLE
    -0.45
    torie
    -0.44
    POSITIVE LOGITS
     peppa
    1.23
     Man
    1.21
     MAN
    1.18
    Man
    1.16
     swarovski
    1.13
     mann
    1.10
     squa
    1.09
     simplif
    1.08
     pixar
    1.08
     uncin
    1.08
    Activations Density 0.120%

    No Known Activations