© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 265
    Prev
    Next
    INDEX
    Explanations

    information related to organizational committees, community events, and procedural guidelines

    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
    2019
    +0.32
    1.9%
    50
    +0.21
    1.2%
    1699
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.32
    0.20
    1699
    +0.21
    0.14
    381
    +0.13
    0.06
    Negative Logits
    <bos>
    -2.72
    ⓧ
    -1.45
    
    -1.34
    /**
    -1.32
    <?
    -1.17
     springfox
    -1.11
    /***
    -1.05
     unve
    -1.03
    <?
    -0.99
     Mlle
    -0.98
    POSITIVE LOGITS
     elektronik
    0.65
     galeria
    0.58
     tonel
    0.58
    H
    0.57
     aparat
    0.57
    C
    0.56
     seksi
    0.55
     balon
    0.55
     sabun
    0.55
     Metode
    0.55
    Activations Density 1.153%

    No Known Activations