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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3691
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing relationships between people

    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
    752
    +0.17
    0.5%
    1034
    +0.11
    0.4%
    897
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.17
    0.06
    752
    +0.11
    0.05
    1034
    +0.11
    0.04
    Negative Logits
    <bos>
    -0.80
    !("{
    -0.67
    #+#
    -0.63
     تانيه
    -0.60
    atschapp
    -0.60
    ्ञ
    -0.58
    ARROLLO
    -0.57
    IBar
    -0.57
    PointerException
    -0.55
    Especies
    -0.55
    POSITIVE LOGITS
     reluct
    1.57
     increa
    1.39
     emphat
    1.39
     intersper
    1.37
     Juf
    1.37
     Abbé
    1.35
     inev
    1.34
     Mlle
    1.33
     disagre
    1.33
     depic
    1.32
    Activations Density 0.233%

    No Known Activations