© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1591
    Prev
    Next
    INDEX
    Explanations

    statements that are deemed reliable or deemed inaccurate

    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
    341
    +0.08
    0.2%
    794
    +0.07
    0.2%
    934
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1604
    +0.08
    0.02
    934
    +0.07
    0.02
    873
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.08
    <?
    -0.66
    lateinit
    -0.58
    fun
    -0.57
    protected
    -0.55
    
    -0.54
     fun
    -0.54
    finally
    -0.51
    ینده
    -0.51
    แท
    -0.51
    POSITIVE LOGITS
     deemed
    2.28
     deem
    2.13
     deems
    1.80
    deemed
    1.64
     sappi
    1.25
     valencia
    1.23
     dispen
    1.19
     nece
    1.15
     ibiza
    1.12
     tramont
    1.12
    Activations Density 0.207%

    No Known Activations