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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5625
    Prev
    Next
    INDEX
    Explanations

    solutions and code snippets to technical programming challenges

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    876
    +0.34
    1.6%
    50
    +0.17
    0.8%
    678
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.34
    -0.06
    872
    +0.17
    0.18
    678
    +0.13
    0.15
    Negative Logits
    <bos>
    -3.81
    Rusia
    -1.07
    República
    -1.05
    SuccessListener
    -1.03
    CompleteListener
    -1.03
    Его
    -0.98
    Pró
    -0.98
    Cuar
    -0.98
    Comun
    -0.97
    Siga
    -0.96
    POSITIVE LOGITS
     increa
    3.29
     affor
    3.24
     milano
    3.20
     maneu
    3.11
     guarante
    3.06
     wien
    3.01
     ?...
    3.01
     madonna
    2.96
     napoli
    2.95
     !...
    2.95
    Activations Density 5.152%

    No Known Activations