© 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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 479
    Prev
    Next
    INDEX
    Explanations

    organizations or programs with acronyms like 'GC' followed by a numerical value

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    554
    +0.09
    0.2%
    1065
    +0.08
    0.2%
    341
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.09
    0.06
    1343
    +0.08
    0.05
    1120
    +0.08
    0.05
    Negative Logits
    <bos>
    -0.88
    marginTop
    -0.58
     tia
    -0.54
    gancia
    -0.54
    DoubleQuotes
    -0.54
    sizeCache
    -0.54
     sár
    -0.54
    EndInit
    -0.52
    borderTop
    -0.52
    protoc
    -0.52
    POSITIVE LOGITS
     Mejía
    1.07
     GC
    1.04
    GC
    1.01
     Weaver
    0.96
     blender
    0.95
     Kes
    0.94
     Darío
    0.94
     Áng
    0.92
     Rama
    0.90
     Cuen
    0.90
    Activations Density 0.320%

    No Known Activations