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

    Neuronpedia

    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. 7325
    Prev
    Next
    INDEX
    Explanations

    phrases indicating pointing or accusation

    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
    410
    +0.13
    0.4%
    559
    +0.12
    0.4%
    395
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.13
    0.03
    559
    +0.12
    0.03
    395
    +0.11
    0.03
    Negative Logits
     silikon
    -0.63
     alkoh
    -0.60
     kompres
    -0.59
     geng
    -0.58
     roh
    -0.55
     nomine
    -0.55
     lagar
    -0.53
     ché
    -0.53
     kask
    -0.53
     dè
    -0.52
    POSITIVE LOGITS
     pointed
    1.15
     pointing
    1.14
    pointed
    0.99
    pointing
    0.99
     points
    0.95
     point
    0.94
     POINT
    0.88
    point
    0.88
    points
    0.88
    Point
    0.86
    Activations Density 0.051%

    No Known Activations