© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3574
    Prev
    Next
    INDEX
    Explanations

    technical details and procedures

    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
    1491
    +0.14
    0.5%
    197
    +0.13
    0.5%
    889
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.14
    0.03
    1491
    +0.13
    0.03
    1810
    +0.11
    0.02
    Negative Logits
    slice
    -0.59
    ModelForm
    -0.57
    try
    -0.55
    mu
    -0.53
    Sc
    -0.52
    Pie
    -0.52
    Mu
    -0.52
    Int
    -0.51
    static
    -0.50
    Si
    -0.50
    POSITIVE LOGITS
     shenan
    1.32
     pamph
    1.30
     Regard
    1.27
     depic
    1.24
     secon
    1.20
     milano
    1.20
     indestru
    1.19
     mosso
    1.19
     fep
    1.19
     fta
    1.18
    Activations Density 0.094%

    No Known Activations