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. 14563
    Prev
    Next
    INDEX
    Explanations

    academic research publication details, such as volume numbers and page references

    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
    410
    +0.15
    0.8%
    680
    +0.15
    0.7%
    1233
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1233
    +0.15
    0.03
    144
    +0.15
    0.03
    410
    +0.14
    0.03
    Negative Logits
    <bos>
    -1.56
    AccessorTable
    -0.71
     مكتبه
    -0.63
     المعرف
    -0.62
    };*/
    -0.58
    ItemBackground
    -0.57
    render
    -0.57
     lenker
    -0.56
    emlrt
    -0.55
    /***
    
    -0.55
    POSITIVE LOGITS
     Vol
    1.48
    Vol
    1.42
     vol
    1.37
     VOL
    1.30
    vol
    1.20
    VOL
    1.10
     Middles
    1.09
     Volk
    1.06
     Vols
    1.02
     Volatility
    0.98
    Activations Density 0.251%

    No Known Activations