Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2805
    Prev
    Next
    INDEX
    Explanations

    descriptions of hidden or rare treasures and architectural or historical gems

    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
    1013
    +0.11
    0.3%
    2034
    +0.09
    0.3%
    260
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1935
    +0.11
    0.04
    1746
    +0.09
    0.03
    284
    +0.09
    0.05
    Negative Logits
     utop
    -1.02
     ordina
    -0.89
     milano
    -0.89
     solidar
    -0.89
     gesta
    -0.86
     gymnas
    -0.85
     hek
    -0.83
     notor
    -0.83
     marte
    -0.83
     grati
    -0.82
    POSITIVE LOGITS
    compromising
    0.57
    葩
    0.56
     among
    0.56
     who
    0.53
    之一
    0.53
     within
    0.53
     amongst
    0.51
     alongside
    0.51
     of
    0.50
     whose
    0.50
    Activations Density 0.369%

    No Known Activations